Simple Tensorflow implementation of "Large Scale GAN Training for High Fidelity Natural Image Synthesis" (BigGAN)

• The paper used orthogonal initialization, but I used random normal initialization. The reason is, when using the orthogonal initialization, it did not train properly.
• I have applied a hierarchical latent space, but not a class embeddedding.

• mnist and cifar10 are used inside keras
• For your dataset, put images like this:

├── dataset    └── YOUR_DATASET_NAME ├── xxx.jpg (name, format doesn't matter) ├── yyy.png └── ... 

• python main.py --phase train --dataset celebA-HQ --gan_type hinge

• python main.py --phase test --dataset celebA-HQ --gan_type hinge

Junho Kim